US5418911A - Data path switch method and apparatus that provides capacitive load isolation - Google Patents

Data path switch method and apparatus that provides capacitive load isolation Download PDF

Info

Publication number
US5418911A
US5418911A US07/896,048 US89604892A US5418911A US 5418911 A US5418911 A US 5418911A US 89604892 A US89604892 A US 89604892A US 5418911 A US5418911 A US 5418911A
Authority
US
United States
Prior art keywords
components
data path
data
component
controller
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Expired - Lifetime
Application number
US07/896,048
Inventor
Anthony M. Zilka
Massoud Taraghi
Paul E. Prince
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Intel Corp
Original Assignee
Intel Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Intel Corp filed Critical Intel Corp
Priority to US07/896,048 priority Critical patent/US5418911A/en
Assigned to INTEL CORPORATION reassignment INTEL CORPORATION ASSIGNMENT OF ASSIGNORS INTEREST. Assignors: PRINCE, PAUL E., TARAGHI, MASSOUD, ZILKA, ANTHONY M.
Priority to US08/388,583 priority patent/US5526497A/en
Application granted granted Critical
Publication of US5418911A publication Critical patent/US5418911A/en
Anticipated expiration legal-status Critical
Expired - Lifetime legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F13/00Interconnection of, or transfer of information or other signals between, memories, input/output devices or central processing units
    • G06F13/38Information transfer, e.g. on bus
    • G06F13/40Bus structure
    • G06F13/4004Coupling between buses
    • G06F13/4022Coupling between buses using switching circuits, e.g. switching matrix, connection or expansion network

Definitions

  • the present invention relates to computer systems. More specifically, the present invention relates to method and apparatus for the exchange of data at a high rate of speed among components within a computer system.
  • a bus is a set of hardware lines or wires used for data transfer among the components of a computer system.
  • a bus is essentially a shared highway that connects different parts of the system, for example the microprocessor, disk drive controller, memory and input/output (I/O) ports, and enables them to transfer information.
  • the bus is commonly specialized for carrying different types of information.
  • One group of wires (actually, traces on a printed circuit board), for example, carries data; another carries the addresses (locations) where specific information can be found; yet another carries control signals to ensure that the different parts of the system use their shared highway without conflict.
  • a communication protocol, or set of rules or standards, for the bus enables the components of the computer to connect with one another and to exchange information with as little error as possible.
  • Buses are characterized by the number of bits they can transfer at a single time.
  • a computer with an 8-bit data bus for example, transfers 8 bits of data at a time, and one with a 16-bit data bus transfers 16 bits at a time.
  • bus is integral to internal data transfer and yet computer users often need to add extra components to the system
  • most microcomputer buses allow for expansion through one or more expansion slots (connectors for add-on circuit boards). Such boards, when they are added, make an electrical connection to the bus and effectively become part of the system.
  • FIG. 1 illustrates a computer system which has components coupled with a bus.
  • bus 20 couples processor 10 to devices 12, 14, 16 and 18.
  • Devices 12, 14, 16 and 18 are representative of generic computer components which exchange data among themselves or with the processor. Examples of devices 12, 14, 16 and 18 include: input/output (I/O) devices, status and control registers, random access memory (RAM) and programmable read only memory (PROM).
  • I/O input/output
  • RAM random access memory
  • PROM programmable read only memory
  • Processor 10 and each of the devices 12, 14, 16, and 18 are connected in parallel to bus 20.
  • Each of the devices 12, 14, 16, and 18 and processor 10 present a capacitive and inductive load to bus 20.
  • Modern processors may run at speeds of approximately 50 megahertz. However, connecting several loads to data bus 20 in parallel creates too much capacitive loading to permit data to be transferred across bus 20 at the operating speed of a 50 megahertz processor 10.
  • bus 24 couples processor 10 and device 18 to bi-directional register 22.
  • Bus 26 couples devices 12, 14 and 16 to bi-directional register 22.
  • bus 20 was presented with five loads (processor 10 and devices 12, 14, 16, and 18).
  • bus 24 is presented with three loads (processor 10, device 18 and bi-directional register 22) and bus 26 is presented with four loads (devices 12, 14, and 16 and bi-directional register 22).
  • bus 24 and bus 26 could each be further subdivided by introducing additional bi-directional registers 22 between the devices attached to them.
  • each bi-directional register 22 has a significant number of parts and therefore this method introduces a significant number of additional chips into the computer system. Each chip consumes area within the computer system which could otherwise be used for other purposes or eliminated to reduce the size of the computer system. Each chip also consumes power which must be provided and produces heat which may have to be dissipated. Furthermore, routing can become an issue because each bi-directional register 22 may have to be routed to different parts all over the board. Therefore, introduction of bi-directional registers 22 increases the complexity of the design of the computer system.
  • An apparatus and method are disclosed for coupling components of a computer system using a data path application specific integrated circuit (ASIC) crossbar switch.
  • a plurality of multi-bit bi-directional register ports are intercoupled using multi-bit multiplexer circuitry.
  • Port selection control signals provided to the multiplexer direct the flow of data through the data path ASIC.
  • the data path ASIC electrically isolates the components of the computer system, thereby minimizing the capacitive load on signal lines and permitting signals to transfer at high rates of speed.
  • Control of the data path ASIC is provided by external circuitry to increase the flexibility of the crossbar switch by removing dependency on any particular communications protocol.
  • Multiple data path ASICs may be combined in parallel to increase bandwidth of data flow by using a bit slice scheme.
  • FIG. 1 illustrates a computer system coupled with a bus.
  • FIG. 2 illustrates a computer system with two buses coupled by a bi-directional register.
  • FIG. 3 illustrates a computer system coupled using a data path ASIC crossbar switch of the present invention.
  • FIG. 4 illustrates circuitry for one embodiment of the data path ASIC of FIG. 3.
  • ASIC application specific integrated circuit
  • FIG. 3 shows a computer system coupled using a data path application specific integrated circuit (ASIC) crossbar switch.
  • processor 10 is coupled to data path ASIC 30 by multi-bit bus 32.
  • Device 18 is coupled to data path ASIC 30 by multi-bit bus 34.
  • Device 16 is also coupled to data path ASIC 30 by bus 36.
  • devices 12 and 14 are coupled to multi-bit bus 38 which is coupled to data path ASIC 30.
  • ASIC application specific integrated circuit
  • Controller 40 is coupled to buses 32, 23, 36 and 38 by control lines 42, 43, 46 and 48 respectively.
  • buses 32, 34, 36 and 38 carry communications protocol signals in addition to the signals to be transferred by data path ASIC 30.
  • controller 40 could receive communications protocol signals directly from processor 10 and devices 12, 14, 16, and 18 instead of indirectly through buses 32, 23, 36 and 38.
  • Controller 40 is also coupled to data path ASIC 30 by multi-bit control line 50. Control of the data path ASIC 30 by controller 40 will be discussed in connection with FIG. 4.
  • FIG. 3 illustrates a data path ASIC 30 coupled to four buses
  • any number of buses can be coupled using a single data path ASIC 30.
  • the nature of integrated circuits is such that there is a maximum number of pins which may provide signals to, or receive signals from, an integrated circuit. Therefore, the state of the art of integrated circuit packaging, and more specifically, the maximum number of pins attainable for an integrated circuit, places an upper bound on the number of data buses which may be intercoupled using a single data path ASIC 30 for a given bandwidth of the buses.
  • bit slicing a technique which is well known in the art, can be used when multiple data path ASICs 30 are combined in parallel.
  • data path ASIC 30 had a 32 bit bandwidth
  • processor 10 and devices 12, 14, 16 and 18 each had 64 bit data paths
  • two 32 bit data path ASICs 30 could be employed in parallel.
  • One data path ASIC 30 could carry the lower 32 bits of the 64 bit data path and the other data path ASIC 30 could carry the upper 32 bits of the 64 bit data path. Since the signals would have identical origins and destinations, controller 40 could provide control for both data path ASICs 30.
  • controller 40 could provide control for both data path ASICs 30.
  • the number of ports for a given maximum number of pins per integrated circuit can be doubled.
  • data path ASIC 30 is able to accommodate communications at any speed below its maximum value (which is typically the maximum value of the processor 10). Not all components of a computer system operate at the high speed typically presented by the processor 10. Therefore, a conventional data bus may be used to intercouple slower devices to one port of the data path ASIC 30. If devices 12 and 14 operated at a slower speed than processor 10, an example of this technique would be bus 38 which intercouples devices 12 and 14.
  • data path ASIC 30 provides an interleave capability.
  • An example of interleaving would be if processor 10 operated at twice the speed of devices 16 and 18. By alternating accesses between the two devices 16 and 18, processor 10 would be able to access one of the two devices 16 and 18 on each clock cycle.
  • Data path ASIC 30 has four ports which correspond to bi-directional registers 52, 54, 56 and 58 which are coupled to buses 32, 23, 36 and 38 respectively.
  • a multi-bit multiplexer 60 is coupled to each of the four bi-directional registers 52, 54, 56 and 58.
  • Multi-bit multiplexer control line 70 is coupled to multiplexer 60 and selectively controls whether multiplexer 60 will permit multi-bit signals to be transmitted from a given port to any other port (or ports).
  • Bi-directional register control lines 62, 64, 66 and 68 are coupled to corresponding bi-directional registers 52, 54, 56 and 58 and enable the registers to latch multi-bit data presented on buses 32, 23, 36 and 38 respectively or from multiplexer 60. Therefore, for example, an enable signal on bi-directional register control line 62 would cause bi-directional register 52 to latch data presented on bus 32 or latch data from multiplexer 60.
  • Bi-directional register control line 62, 64, 66 and 68 and multiplexer control line 70 together form control line 50 of FIG. 3.
  • control of data path ASIC 30 by controller 40 while dependent upon the particular communications protocol of the processor 10 or devices 12, 14, 16, and 18, is relatively simple and best illustrated by example of representative read and write operations.
  • the examples are representative of generic read and write operations.
  • control of the data path ASIC 30 would depend upon the communication protocol of the processor 10 or devices 12, 14, 16 and 18 to be coupled. Actual communications protocols are well known in the art and the example read and write operations have been kept simple for ease of understanding.
  • processor 10 will read data from device 18. The read is initiated by processor 10 signaling controller 40 through control line 42 that it will read device 18. Upon sensing the read request from processor 10, controller 40 will use control line 44 to enable device 18 thereby causing device 18 to drive the requested data onto bus 34.
  • controller 40 will use bi-directional register control line 64 to signal bi-directional register 54 to latch the requested data.
  • controller 40 will use multiplexer control line 70 to signal multiplexer 60 and thereby set multiplexer 60 so that bi-directional register 54 is coupled to bi-directional register 52.
  • the controller will use bi-directional register control line 62 to enable bi-directional register 52 thereby causing bi-directional register 52 to drive the requested data to processor 10 through bus 32.
  • controller 40 will use control line 42 to signal processor 10 that the processor has the data which it requested. In this way, data can be read at a high rate of speed with a latency penalty of only one clock cycle.
  • processor 10 will write data to device 18.
  • the write is initiated by processor 10 signaling controller 40 through control line 42 that it will write to device 18.
  • controller 40 Upon sensing the write request from processor 10, controller 40 will use control line 42 to enable processor 10 thereby causing processor 10 to drive the data to be written onto bus 32.
  • controller 40 will use bi-directional register control line 62 to signal bi-directional register 52 to latch the data to be written.
  • controller 40 will use multiplexer control line 70 to signal multiplexer 60 and thereby set multiplexer 60 so that bi-directional register 52 is coupled to bi-directional register 54.
  • the controller will use bi-directional register control line 64 to enable bi-directional register 54 thereby causing bi-directional register 54 to drive the data to be written to device 18 through bus 34.
  • controller 40 would use control line 42 to signal processor 10 that the device has received the data which was to be written. In this way, data can be written with a latency penalty of only one clock cycle.

Abstract

Components of a computer system are coupled using a data path application specific integrated circuit (ASIC) crossbar switch. A plurality of multi-bit bi-directional register ports are intercoupled using multi-bit multiplexer circuitry. Port selection control signals provided to the multiplexer direct the flow of data through the data path ASIC. The data path ASIC electrically isolates the components of the computer system, thereby minimizing the capacitive load on signal lines and permitting signals to transfer at high rates of speed. Control of the data path ASIC is provided by external circuitry to increase the flexibility of the crossbar switch by removing dependency on any particular communications protocol. Multiple data path ASICs may be combined in parallel to increase bandwidth of data flow by using a bit slice scheme.

Description

BACKGROUND OF THE INVENTION su (1) Field of the Invention
The present invention relates to computer systems. More specifically, the present invention relates to method and apparatus for the exchange of data at a high rate of speed among components within a computer system.
(2) Art Background
Data buses are used commonly throughout the computer industry. A bus is a set of hardware lines or wires used for data transfer among the components of a computer system. A bus is essentially a shared highway that connects different parts of the system, for example the microprocessor, disk drive controller, memory and input/output (I/O) ports, and enables them to transfer information. Usually supervised by the microprocessor, the bus is commonly specialized for carrying different types of information. One group of wires (actually, traces on a printed circuit board), for example, carries data; another carries the addresses (locations) where specific information can be found; yet another carries control signals to ensure that the different parts of the system use their shared highway without conflict. A communication protocol, or set of rules or standards, for the bus enables the components of the computer to connect with one another and to exchange information with as little error as possible.
Buses are characterized by the number of bits they can transfer at a single time. A computer with an 8-bit data bus, for example, transfers 8 bits of data at a time, and one with a 16-bit data bus transfers 16 bits at a time.
Because the bus is integral to internal data transfer and yet computer users often need to add extra components to the system, most microcomputer buses allow for expansion through one or more expansion slots (connectors for add-on circuit boards). Such boards, when they are added, make an electrical connection to the bus and effectively become part of the system.
FIG. 1 illustrates a computer system which has components coupled with a bus. In the Figure, bus 20 couples processor 10 to devices 12, 14, 16 and 18. Devices 12, 14, 16 and 18 are representative of generic computer components which exchange data among themselves or with the processor. Examples of devices 12, 14, 16 and 18 include: input/output (I/O) devices, status and control registers, random access memory (RAM) and programmable read only memory (PROM).
Processor 10 and each of the devices 12, 14, 16, and 18 are connected in parallel to bus 20. Each of the devices 12, 14, 16, and 18 and processor 10 present a capacitive and inductive load to bus 20. Modern processors may run at speeds of approximately 50 megahertz. However, connecting several loads to data bus 20 in parallel creates too much capacitive loading to permit data to be transferred across bus 20 at the operating speed of a 50 megahertz processor 10.
Referring now to FIG. 2, a computer system with two buses coupled by a bi-directional register is illustrated. In the figure, bus 24 couples processor 10 and device 18 to bi-directional register 22. Bus 26 couples devices 12, 14 and 16 to bi-directional register 22. By introducing a bi-directional register 22, and two separate buses 24 and 26, the load on each bus is decreased, thereby permitting faster communication along each bus.
In the example of FIG. 1, bus 20 was presented with five loads (processor 10 and devices 12, 14, 16, and 18). In the configuration of FIG. 2, bus 24 is presented with three loads (processor 10, device 18 and bi-directional register 22) and bus 26 is presented with four loads ( devices 12, 14, and 16 and bi-directional register 22). Thus, while the total number of loads in the system has increased, the load on any given bus has decreased thereby permitting each bus to operate at a higher speed. While only one bi-directional register 22 has been introduced for ease of understanding, bus 24 and bus 26 could each be further subdivided by introducing additional bi-directional registers 22 between the devices attached to them.
While the introduction of one or more bi-directional registers 22 increases the speed at which each individual data bus can operate, there is a complexity penalty and a latency penalty which much be paid. The complexity penalty has several parts. First, each bi-directional register 22 has a significant number of parts and therefore this method introduces a significant number of additional chips into the computer system. Each chip consumes area within the computer system which could otherwise be used for other purposes or eliminated to reduce the size of the computer system. Each chip also consumes power which must be provided and produces heat which may have to be dissipated. Furthermore, routing can become an issue because each bi-directional register 22 may have to be routed to different parts all over the board. Therefore, introduction of bi-directional registers 22 increases the complexity of the design of the computer system.
Furthermore, there is latency penalty because, while the load has been reduced, signals will probably have to travel through one or more bi-directional registers 22.
SUMMARY OF THE INVENTION
It is therefore an object of the present invention to couple several computer components together in a manner whereby each component is electrically isolated from the capacitive load of the other components thereby achieving high-speed data transfer among the components.
It is a further object of the present invention to couple the components of a computer system in a manner which minimizes design complexity and signal transfer latency.
It is a further object of the present invention to create a flexible, generic intercoupling device which does not contain logic dependent upon the communication protocol of each device to be coupled.
An apparatus and method are disclosed for coupling components of a computer system using a data path application specific integrated circuit (ASIC) crossbar switch. A plurality of multi-bit bi-directional register ports are intercoupled using multi-bit multiplexer circuitry. Port selection control signals provided to the multiplexer direct the flow of data through the data path ASIC.
The data path ASIC electrically isolates the components of the computer system, thereby minimizing the capacitive load on signal lines and permitting signals to transfer at high rates of speed. Control of the data path ASIC is provided by external circuitry to increase the flexibility of the crossbar switch by removing dependency on any particular communications protocol.
Multiple data path ASICs may be combined in parallel to increase bandwidth of data flow by using a bit slice scheme.
BRIEF DESCRIPTION OF THE DRAWINGS
The objects, features and advantages of the method and apparatus of the present invention will be apparent from the following detailed description of the invention in which:
FIG. 1 illustrates a computer system coupled with a bus.
FIG. 2 illustrates a computer system with two buses coupled by a bi-directional register.
FIG. 3 illustrates a computer system coupled using a data path ASIC crossbar switch of the present invention.
FIG. 4 illustrates circuitry for one embodiment of the data path ASIC of FIG. 3.
DETAILED DESCRIPTION OF THE INVENTION
An apparatus and method is disclosed for intercoupling components of a computer system using a data path application specific integrated circuit (ASIC). In the following description, for the purposes of explanation, specific devices, signals and data structures are disclosed in order to more thoroughly understand the present invention. However, it will be apparent to one skilled in the art that the present invention may be practiced without the specific details. In other instances, well-known circuits and data structures are not disclosed herein to avoid obscuring the present invention unnecessarily.
FIG. 3 shows a computer system coupled using a data path application specific integrated circuit (ASIC) crossbar switch. In the figure, processor 10 is coupled to data path ASIC 30 by multi-bit bus 32. Device 18 is coupled to data path ASIC 30 by multi-bit bus 34. Device 16 is also coupled to data path ASIC 30 by bus 36. Furthermore, devices 12 and 14 are coupled to multi-bit bus 38 which is coupled to data path ASIC 30.
Controller 40 is coupled to buses 32, 23, 36 and 38 by control lines 42, 43, 46 and 48 respectively. In this example, it is assumed that buses 32, 34, 36 and 38 carry communications protocol signals in addition to the signals to be transferred by data path ASIC 30. However, it will be obvious to one skilled in the art that, in an alternate embodiment, controller 40 could receive communications protocol signals directly from processor 10 and devices 12, 14, 16, and 18 instead of indirectly through buses 32, 23, 36 and 38. Controller 40 is also coupled to data path ASIC 30 by multi-bit control line 50. Control of the data path ASIC 30 by controller 40 will be discussed in connection with FIG. 4.
While the embodiment of FIG. 3 illustrates a data path ASIC 30 coupled to four buses, it will be obvious to one skilled in the art that, conceptually, any number of buses can be coupled using a single data path ASIC 30. However, the nature of integrated circuits is such that there is a maximum number of pins which may provide signals to, or receive signals from, an integrated circuit. Therefore, the state of the art of integrated circuit packaging, and more specifically, the maximum number of pins attainable for an integrated circuit, places an upper bound on the number of data buses which may be intercoupled using a single data path ASIC 30 for a given bandwidth of the buses.
However, it will be obvious to one skilled in the art that a limit on the number of ports for data path ASIC 30 is not onerous for two reasons. First, "bit slicing", a technique which is well known in the art, can be used when multiple data path ASICs 30 are combined in parallel. Thus, if data path ASIC 30 had a 32 bit bandwidth, and processor 10 and devices 12, 14, 16 and 18 each had 64 bit data paths, two 32 bit data path ASICs 30 could be employed in parallel. One data path ASIC 30 could carry the lower 32 bits of the 64 bit data path and the other data path ASIC 30 could carry the upper 32 bits of the 64 bit data path. Since the signals would have identical origins and destinations, controller 40 could provide control for both data path ASICs 30. In this example, by using two 32 bit data path ASICs 30 in parallel, instead of one 64 bit data path ASIC 30, the number of ports for a given maximum number of pins per integrated circuit can be doubled.
Secondly, data path ASIC 30 is able to accommodate communications at any speed below its maximum value (which is typically the maximum value of the processor 10). Not all components of a computer system operate at the high speed typically presented by the processor 10. Therefore, a conventional data bus may be used to intercouple slower devices to one port of the data path ASIC 30. If devices 12 and 14 operated at a slower speed than processor 10, an example of this technique would be bus 38 which intercouples devices 12 and 14.
Furthermore, the ability of data path ASIC 30 to accommodate communications at any speed below its maximum provides an interleave capability. An example of interleaving would be if processor 10 operated at twice the speed of devices 16 and 18. By alternating accesses between the two devices 16 and 18, processor 10 would be able to access one of the two devices 16 and 18 on each clock cycle.
Referring now to FIG. 4, the circuitry for the data path ASIC 30 of FIG. 3 is illustrated. Data path ASIC 30 has four ports which correspond to bi-directional registers 52, 54, 56 and 58 which are coupled to buses 32, 23, 36 and 38 respectively. A multi-bit multiplexer 60 is coupled to each of the four bi-directional registers 52, 54, 56 and 58. Multi-bit multiplexer control line 70 is coupled to multiplexer 60 and selectively controls whether multiplexer 60 will permit multi-bit signals to be transmitted from a given port to any other port (or ports).
Bi-directional register control lines 62, 64, 66 and 68 are coupled to corresponding bi-directional registers 52, 54, 56 and 58 and enable the registers to latch multi-bit data presented on buses 32, 23, 36 and 38 respectively or from multiplexer 60. Therefore, for example, an enable signal on bi-directional register control line 62 would cause bi-directional register 52 to latch data presented on bus 32 or latch data from multiplexer 60.
Bi-directional register control line 62, 64, 66 and 68 and multiplexer control line 70 together form control line 50 of FIG. 3.
Referring back to FIG. 3, control of data path ASIC 30 by controller 40, while dependent upon the particular communications protocol of the processor 10 or devices 12, 14, 16, and 18, is relatively simple and best illustrated by example of representative read and write operations. The examples are representative of generic read and write operations. In an actual implementation, control of the data path ASIC 30 would depend upon the communication protocol of the processor 10 or devices 12, 14, 16 and 18 to be coupled. Actual communications protocols are well known in the art and the example read and write operations have been kept simple for ease of understanding.
In the first example, processor 10 will read data from device 18. The read is initiated by processor 10 signaling controller 40 through control line 42 that it will read device 18. Upon sensing the read request from processor 10, controller 40 will use control line 44 to enable device 18 thereby causing device 18 to drive the requested data onto bus 34.
Referring now to FIG. 4 again, once the requested data is present on bus 34, controller 40 will use bi-directional register control line 64 to signal bi-directional register 54 to latch the requested data. After the requested data has been loaded into register 54, controller 40 will use multiplexer control line 70 to signal multiplexer 60 and thereby set multiplexer 60 so that bi-directional register 54 is coupled to bi-directional register 52. Next the controller will use bi-directional register control line 62 to enable bi-directional register 52 thereby causing bi-directional register 52 to drive the requested data to processor 10 through bus 32. Finally, controller 40 will use control line 42 to signal processor 10 that the processor has the data which it requested. In this way, data can be read at a high rate of speed with a latency penalty of only one clock cycle.
In the second example, referring again to FIG. 3, processor 10 will write data to device 18. The write is initiated by processor 10 signaling controller 40 through control line 42 that it will write to device 18. Upon sensing the write request from processor 10, controller 40 will use control line 42 to enable processor 10 thereby causing processor 10 to drive the data to be written onto bus 32.
Referring now to FIG. 4, once the data to be written is present on bus 32, controller 40 will use bi-directional register control line 62 to signal bi-directional register 52 to latch the data to be written. After the data to be written has been loaded into register 52, controller 40 will use multiplexer control line 70 to signal multiplexer 60 and thereby set multiplexer 60 so that bi-directional register 52 is coupled to bi-directional register 54. Next the controller will use bi-directional register control line 64 to enable bi-directional register 54 thereby causing bi-directional register 54 to drive the data to be written to device 18 through bus 34. Finally, controller 40 would use control line 42 to signal processor 10 that the device has received the data which was to be written. In this way, data can be written with a latency penalty of only one clock cycle.
While the present invention has been particularly described with reference to FIGS. 3-4 and with emphasis on certain computer architecture, it should be understood that the figures are for illustration purpose only and should not be taken as limitations upon the present invention. In addition, it is clear that the method and apparatus of the present invention has utility in any application where high speed transfer of data is desired. It is contemplated that numerous alternatives, modifications, variations and uses may be made, by one skilled in the art, without departing from the spirit and scope of the invention as disclosed above.

Claims (20)

What is claimed is:
1. A method for intercoupling at least three computer components for transfer of data signals among the components, each of the components having a capacitive load, the method comprising the steps of:
coupling a data path means to the components, the data path means for electrically isolating each of the components such that the capacitive loads of the components cannot combine, the data path means for permitting the data signals to be selectively transferred through the data path means between first and second components of the components and between the first and a third component of the components;
coupling a controller means to the components, and to the data path means, the controller means for selectively controlling the data signal transfers through the data path means between the first and second components and between the first and third components;
the first component notifying the controller means when the first component is to receive the data signals from the second component;
the controller means, in response, instructing the data path means to receive the data signals from the second component, and instructing the second component to send the data signals to the data path means;
the second component, in response, sending the data signals to the data path means;
the controller means, in response, instructing the data path means to divert the data signals to the first component, and instructing the first component to receive the data signals from the data path means; and
the first component, in response, receiving the data signals from the data path means.
2. A method for intercoupling at least three computer components for transfer of data signals among the components, each of the components having a capacitive load, the method comprising the steps of:
coupling a data path means to the components, the data path means for electrically isolating each of the components such that the capacitive loads of the components cannot combine, the data path means for permitting the data signals to be selectively transferred through the data path means between first and second components of the components and between the first and a third component of the components;
coupling a controller means to the components, and to the data path means, the controller means for selectively controlling the data signal transfers through the data path means between the first and second components and between the first and third components;
the first component notifying the controller means when the first component is to send data signals to the second component;
the controller means, in response, instructing the data path means to receive the data signals from the first component;
the first component, in response, sending the data signals to the data path means;
the controller means, in response, instructing the data path means to divert the data signals to the second component and instructing the second component to receive the data signals from the data path means; and
the second component, in response, receiving the data signals from the data path means.
3. A method for intercoupling at least three computer components for transfer of data signals among the components, each of the components having a capacitive load, the method comprising the steps of:
coupling a data path means to the components, the data path means for electrically isolating each of the components such that the capacitive loads of the components cannot combine, the data path means for permitting the data signals to be selectively transferred through the data path means between first and second components of the components and between the first and a third component of the components;
coupling a controller means to the components, and to the data path means, the controller means for selectively controlling the data signal transfers through the data path means between the first and second components and between the first and third components; and
distributing the data signals among at least two of the components alternately such that the data signals interleave.
4. A method for intercoupling at least three computer components for transfer of data signals among the components, each of the components having a capacitive load, the method comprising the steps of:
coupling a data path means to the components, the data path means for electrically isolating each of the components such that the capacitive loads of the components cannot combine, the data path means for permitting the data signals to be selectively transferred through the data path means between first and second components of the components and between the first and a third component of the components;
coupling a controller means to the components, and to the data path means, the controller means for selectively controlling the data signal transfers through the data path means between the first and second components and between the first and third components; and
the controller means controlling a plurality of data path means, each of the data path means corresponding to one data signal subset.
5. An apparatus for intercoupling at least three computer components, each of the components having a capacitive load, said apparatus comprising:
a data path means, coupled to the components, the data path means for electrically isolating each of the components such that the capacitive loads of the components cannot combine, the data path means for permitting the data signals to be selectively transferred through the data path means between first and second components of the components and between the first and a third component of the components;
a controller means coupled to the components, and to the data path means, the controller means for selectively controlling the data signal transfers through the data path means between the first and second components and between the first and third components, wherein,
the first component notifies the controller means when the first component is to receive the data signals from the second component;
the controller means, in response, instructs the data path means to receive the data signals from the second component, and instructs the second component to send the data signals to the data path means;
the second component, in response, sends the data signals to the data path means;
the controller means, in response, instructs the data path means to divert the data signals to the first component, and instructs the first component to receive the data signals from the data path means; and
the first component, in response, receives the data signals from the data path means.
6. An apparatus for intercoupling at least three computer components, each of the components having a capacitive load, said apparatus comprising:
a data path means, coupled to the components, the data path means for electrically isolating each of the components such that the capacitive loads of the components cannot combine, the data path means for permitting the data signals to be selectively transferred through the data path means between first and second components of the components and between the first and a third component of the components;
a controller means coupled to the components, and to the data path means, the controller means for selectively controlling the data signal transfers through the data path means between the first and second components and between the first and third components, wherein,
the first component notifies the controller means when the first component is to send the data signals to the second component;
the controller means, in response, instructs the data path means to receive the data signals from the first component;
the first component, in response, sends the data signals to the data path means;
the controller means, in response, instructs the data path means to divert the data signals to the second component, and instructs the second component to receive the data signals from the data path means; and
the second component, in response, receives the data signals from the data path means.
7. An apparatus for intercoupling at least three computer components, each of the components having a capacitive load, said apparatus comprising:
a data path means, coupled to the components, the data path means for electrically isolating each of the components such that the capacitive loads of the components cannot combine, the data path means for permitting the data signals to be selectively transferred through the data path means between first and second components of the components and between the first and a third component of the components;
a controller means coupled to the components, and to the data path means, the controller means for selectively controlling the data signal transfers through the data path means between the first and second components and between the first and third components, wherein the data path means is comprised of:
a plurality of buffer means for receiving and holding the data signals from a corresponding computer component of the components, there being one buffer means for each of the components, each buffer means coupled to the corresponding computer component and to the controller means, each buffer means for holding and releasing the data signals at the behest of the controller means; and
switching means, coupled to each of the buffer means and to the controller means, for selectively diverting the flow of the data signals from any buffer means to any other buffer means at the behest of the controller means.
8. The apparatus as set forth in claim 7 wherein at least one of the buffer means is bi-directional.
9. The apparatus as set forth in claim 7 wherein the switching means is a multiplexer.
10. An apparatus for intercoupling at least three computer components, each of the components having a capacitive load, said apparatus comprising:
a data path means, coupled to the components, the data path means for electrically isolating each of the components such that the capacitive loads of the components cannot combine, the data path means for permitting the data signals to be selectively transferred through the data path means between first and second components of the components and between the first and a third component of the components;
a controller means coupled to the components, and to the data path means, the controller means for selectively controlling the data signal transfers through the data path means between the first and second components and between the first and third components, wherein the data signals are distributed among at least two of the components alternately such that the data signals interleave.
11. An apparatus for intercoupling at least three computer components, each of the components having a capacitive load, said apparatus comprising:
a data path means, coupled to the components, the data path means for electrically isolating each of the components such that the capacitive loads of the components cannot combine, the data path means for permitting the data signals to be selectively transferred through the data path means between first and second components of the components and between the first and a third component of the components;
a controller means coupled to the components, and to the data path means, the controller means for selectively controlling the data signal transfers through the data path means between the first and second components and between the first and third components, wherein the data signals comprise a plurality of data signal subsets and the controller means controls a plurality of data path means, each of the data path means corresponding to one of the data signal subsets.
12. An apparatus for intercoupling at least three computer components, each of the components having a capacitive load, said apparatus comprising:
a data path means, coupled to the components, the data path means for electrically isolating each of the components such that the capacitive loads of the components cannot combine, the data path means for permitting the data signals to be selectively transferred through the data path means between first and second components of the components and between the first and a third component of the components;
a controller means coupled to the components, and to the data path means, the controller means for selectively controlling the data signal transfers through the data path means between the first and second components and between the first and third components, wherein at least one of the components comprises:
a first sub-component; and
a second sub-component coupled to the first sub-component.
13. An apparatus for intercoupling at least three computer components, each of the components having a capacitive load, said apparatus comprising:
a data path integrated circuit, coupled to the components, the data path integrated circuit capable of electrically isolating each of the components such that the capacitive loads of the components cannot combine, the data path integrated circuit capable of permitting the data signals to be selectively transferred through the data path integrated circuit between first and second components of the components and between the first and a third component of the components; and
a controller coupled to the components, and to the data path integrated circuit, the controller capable of selectively controlling the data signal transfers through the data path integrated circuit between the first and second components and between the first and third components, wherein,
the first component notifies the controller when it is to receive the data signals from the second component;
the controller, in response, instructs the data path integrated circuit to receive the data signals from the second component, and instructs the second component to send the data signals to the data path integrated circuit;
the second component, in response, sends the data signals to the data path integrated circuit;
the controller means, in response, instructs the data path integrated circuit to divert the data signals to the first component, and instructs the first component to receive the signals from the data path integrated circuit; and
the first component, in response, receives the data signals from the data path integrated circuit.
14. An apparatus for intercoupling at least three computer components, each of the components having a capacitive load, said apparatus comprising:
a data path integrated circuit, coupled to the components, the data path integrated circuit capable of electrically isolating each of the components such that the capacitive loads of the components cannot combine, the data path integrated circuit capable of permitting the data signals to be selectively transferred through the data path integrated circuit between first and second components of the components and between the first and a third component of the components; and
a controller coupled to the components, and to the data path integrated circuit, the controller capable of selectively controlling the data signal transfers through the data path integrated circuit between the first and second components and between the first and third components, wherein,
the first component notifies the controller when it is to send the data signals to the second component;
the controller, in response, instructs the data path integrated circuit to receive the data signals from the first component;
the first component, in response, sends the data signals to the data path integrated circuit;
the controller, in response, instructs the data path integrated circuit to divert the data signals to the second component, and instructs the second component to receive the data signals from the data path integrated circuit; and
the second component, in response, receives the data signals from the data path integrated circuit.
15. An apparatus for intercoupling at least three computer components, each of the components having a capacitive load, said apparatus comprising:
a data path integrated circuit, coupled to the components, the data path integrated circuit capable of electrically isolating each of the components such that the capacitive loads of the components cannot combine, the data path integrated circuit capable of permitting the data signals to be selectively transferred through the data path integrated circuit between first and second components of the components and between the first and a third component of the components; and
a controller coupled to the components, and to the data path integrated circuit, the controller capable of selectively controlling the data signal transfers through the data path integrated circuit between the first and second components and between the first and third components wherein the data path integrated circuit is comprised of:
a plurality of buffers capable of receiving and holding the data signals from a corresponding computer component of the components, there being one buffer for each of the components, each buffer coupled to the corresponding computer component and to the controller, each buffer holding and releasing the data signals at the behest of the controller; and
a switch, coupled to each of the buffers and to the controller, the switch capable of selectively diverting the flow of the data signals from any buffer means to any other buffer means at the behest of the controller.
16. The apparatus as set forth in claim 15 wherein at least one of the buffers is bi-directional.
17. The apparatus as set forth in claim 15 wherein the switch is a multiplexer.
18. An apparatus for intercoupling at least three computer components, each of the components having a capacitive load, said apparatus comprising:
a data path integrated circuit, coupled to the components, the data path integrated circuit capable of electrically isolating each of the components such that the capacitive loads of the components cannot combine, the data path integrated circuit capable of permitting the data signals to be selectively transferred through the data path integrated circuit between first and second components of the components and between the first and a third component of the components; and
a controller coupled to the components, and to the data path integrated circuit, the controller capable of selectively controlling the data signal transfers through the data path integrated circuit between the first and second components and between the first and third components wherein the data signals are distributed among at least two of the components alternately such that the data signals interleave.
19. An apparatus for intercoupling at least three computer components, each of the components having a capacitive load, said apparatus comprising:
a data path integrated circuit, coupled to the components, the data path integrated circuit capable of electrically isolating each of the components such that the capacitive loads of the components cannot combine, the data path integrated circuit capable of permitting the data signals to be selectively transferred through the data path integrated circuit between first and second components of the components and between the first and a third component of the components; and
a controller coupled to the components, and to the data path integrated circuit, the controller capable of selectively controlling the data signal transfers through the data path integrated circuit between the first and second components and between the first and third components wherein the data signals comprise a plurality of data signal subsets and the controller controls a plurality of data path integrated circuits, each of the data path integrated circuits corresponding to one of the data signal subsets.
20. An apparatus for intercoupling at least three computer components, each of the components having a capacitive load, said apparatus comprising:
a data path integrated circuit, coupled to the components, the data path integrated circuit capable of electrically isolating each of the components such that the capacitive loads of the components cannot combine, the data path integrated circuit capable of permitting the data signals to be selectively transferred through the data path integrated circuit between first and second components of the components and between the first and a third component of the components; and
a controller coupled to the components, and to the data path integrated circuit, the controller capable of selectively controlling the data signal transfers through the data path integrated circuit between the first and second components and between the first and third components wherein at least one of the components comprises:
a first sub-component; and
a second sub-component coupled to the first sub-component.
US07/896,048 1992-06-09 1992-06-09 Data path switch method and apparatus that provides capacitive load isolation Expired - Lifetime US5418911A (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
US07/896,048 US5418911A (en) 1992-06-09 1992-06-09 Data path switch method and apparatus that provides capacitive load isolation
US08/388,583 US5526497A (en) 1992-06-09 1995-02-09 System having switch that provides capacitive load isolation

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
US07/896,048 US5418911A (en) 1992-06-09 1992-06-09 Data path switch method and apparatus that provides capacitive load isolation

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US08/388,583 Continuation US5526497A (en) 1992-06-09 1995-02-09 System having switch that provides capacitive load isolation

Publications (1)

Publication Number Publication Date
US5418911A true US5418911A (en) 1995-05-23

Family

ID=25405536

Family Applications (2)

Application Number Title Priority Date Filing Date
US07/896,048 Expired - Lifetime US5418911A (en) 1992-06-09 1992-06-09 Data path switch method and apparatus that provides capacitive load isolation
US08/388,583 Expired - Lifetime US5526497A (en) 1992-06-09 1995-02-09 System having switch that provides capacitive load isolation

Family Applications After (1)

Application Number Title Priority Date Filing Date
US08/388,583 Expired - Lifetime US5526497A (en) 1992-06-09 1995-02-09 System having switch that provides capacitive load isolation

Country Status (1)

Country Link
US (2) US5418911A (en)

Cited By (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5572685A (en) * 1994-03-23 1996-11-05 International Computers Limited Computer system
US5611053A (en) * 1994-01-21 1997-03-11 Advanced Micro Devices, Inc. Apparatus and method for integrating bus master ownership of local bus load by plural data transceivers
US5638521A (en) * 1992-10-12 1997-06-10 Leunig Gmbh Apparatus using a parallel interface for data transfer between a plurality of computers, as well as for transfer of data from computers to shared peripheral devices
US5661413A (en) * 1994-06-06 1997-08-26 Matsushita Electric Industrial Co., Ltd. Processor utilizing a low voltage data circuit and a high voltage controller
US5664123A (en) * 1994-09-06 1997-09-02 Pitney Bowes Inc. Digital communication I/O port
US5783963A (en) * 1996-02-29 1998-07-21 Lexmark International, Inc. ASIC with selectable output drivers
US5793656A (en) * 1994-06-30 1998-08-11 Hughes Electronics Corporation Application-specific integrated circuits having programming functions
US5949982A (en) * 1997-06-09 1999-09-07 International Business Machines Corporation Data processing system and method for implementing a switch protocol in a communication system
US6029242A (en) * 1995-08-16 2000-02-22 Sharp Electronics Corporation Data processing system using a shared register bank and a plurality of processors
US6101561A (en) * 1998-02-06 2000-08-08 International Business Machines Corporation System for providing an increase in digital data transmission rate over a parallel bus by converting binary format voltages to encoded analog format currents
US6530033B1 (en) * 1999-10-28 2003-03-04 Hewlett-Packard Company Radial arm memory bus for a high availability computer system
US8769231B1 (en) * 2008-07-30 2014-07-01 Xilinx, Inc. Crossbar switch device for a processor block core
US20150205740A1 (en) * 2012-01-31 2015-07-23 Hewlett-Packard Development Company, L.P. Flexible port configuration based on interface coupling

Families Citing this family (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5813037A (en) * 1995-03-30 1998-09-22 Intel Corporation Multi-port register file for a reservation station including a pair of interleaved storage cells with shared write data lines and a capacitance isolation mechanism
US6370605B1 (en) 1999-03-04 2002-04-09 Sun Microsystems, Inc. Switch based scalable performance storage architecture
US6349357B1 (en) * 1999-03-04 2002-02-19 Sun Microsystems, Inc. Storage architecture providing scalable performance through independent control and data transfer paths
US6397267B1 (en) 1999-03-04 2002-05-28 Sun Microsystems, Inc. Redirected I/O for scalable performance storage architecture
TW436695B (en) * 1999-09-28 2001-05-28 Geneticware Co Ltd Data process system having an architecture for allocating data/address channel
US6604155B1 (en) 1999-11-09 2003-08-05 Sun Microsystems, Inc. Storage architecture employing a transfer node to achieve scalable performance
US6711719B2 (en) 2001-08-13 2004-03-23 International Business Machines Corporation Method and apparatus for reducing power consumption in VLSI circuit designs
US6874050B2 (en) * 2002-01-16 2005-03-29 Hewlett-Packard Development Company, L.P. Circuit and method for expanding a serial bus
US7310317B2 (en) * 2002-02-25 2007-12-18 Motorola, Inc. Apparatus and method for de-prioritization of bypass packets in a packet based communication system
US6816939B2 (en) * 2002-05-09 2004-11-09 International Business Machines Corporation Apparatus for supporting I2C bus masters on a secondary side of an I2C multiplexor
US8721203B2 (en) * 2005-10-06 2014-05-13 Zih Corp. Memory system and method for consumables of a printer
US8788756B2 (en) * 2011-11-28 2014-07-22 Xilinx, Inc. Circuit for and method of enabling the transfer of data by an integrated circuit

Citations (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US3761633A (en) * 1970-07-21 1973-09-25 Siemens Ag Time multiplex coupling arrangement for the connection of multiple buses of a time multiplex telephone exchange
US4445048A (en) * 1980-04-04 1984-04-24 Rolm Corporation High speed ribbon cable bus
US4608504A (en) * 1983-01-20 1986-08-26 Sharp Kabushiki Kaisha Interface circuit for interconnecting peripherals to an information processing device
US4788638A (en) * 1985-12-13 1988-11-29 Hitachi, Limited Data transfer apparatus between input/output devices and main storage with channel devices being of a concentrated type and stand-alone type
US4852083A (en) * 1987-06-22 1989-07-25 Texas Instruments Incorporated Digital crossbar switch
US4860244A (en) * 1983-11-07 1989-08-22 Digital Equipment Corporation Buffer system for input/output portion of digital data processing system
US4885799A (en) * 1987-07-01 1989-12-05 Motorola, Inc. Load pull isolation switch for a fast locking synthesizer
US4903259A (en) * 1987-07-24 1990-02-20 Nec Corporation Time-division multiplex switching network
US4987319A (en) * 1988-09-08 1991-01-22 Kawasaki Steel Corporation Programmable input/output circuit and programmable logic device
US5046041A (en) * 1987-12-17 1991-09-03 Automobiles Peugeot Device for transmitting information between a plurality of elements of an automobile vehicle, and a central information processing unit
US5058072A (en) * 1988-06-01 1991-10-15 Nec Corporation Semiconductor memory device with high speed sensing facility
US5079693A (en) * 1989-02-28 1992-01-07 Integrated Device Technology, Inc. Bidirectional FIFO buffer having reread and rewrite means
US5087900A (en) * 1990-11-19 1992-02-11 Reliability Incorporated Transmission line network for multiple capacitive loads
US5109333A (en) * 1988-04-15 1992-04-28 Hitachi, Ltd. Data transfer control method and apparatus for co-processor system
US5191656A (en) * 1991-08-29 1993-03-02 Digital Equipment Corporation Method and apparatus for shared use of a multiplexed address/data signal bus by multiple bus masters

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US3697702A (en) * 1970-07-16 1972-10-10 American Telephone & Telegraph Selectably controllable announcement system
US4410961A (en) * 1981-02-17 1983-10-18 Pitney Bowes Inc. Interface between a processor system and peripheral devices used in a mailing system
US4442502A (en) * 1981-03-30 1984-04-10 Datapoint Corporation Digital information switching system
SE462361B (en) * 1988-03-30 1990-06-11 Ellemtel Utvecklings Ab PAKETDATAVAELJARE
US5220566A (en) * 1989-02-10 1993-06-15 Minolta Camera Kabushiki Kaisha Multiplexer for use in data processing system
US5274773A (en) * 1990-11-09 1993-12-28 Conner Peripherals, Inc. Flexible host interface controller architecture
US5334881A (en) * 1992-03-19 1994-08-02 The United States Of America As Represented By The Secretary Of The Navy High isolation electronic switch

Patent Citations (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US3761633A (en) * 1970-07-21 1973-09-25 Siemens Ag Time multiplex coupling arrangement for the connection of multiple buses of a time multiplex telephone exchange
US4445048A (en) * 1980-04-04 1984-04-24 Rolm Corporation High speed ribbon cable bus
US4608504A (en) * 1983-01-20 1986-08-26 Sharp Kabushiki Kaisha Interface circuit for interconnecting peripherals to an information processing device
US4860244A (en) * 1983-11-07 1989-08-22 Digital Equipment Corporation Buffer system for input/output portion of digital data processing system
US4788638A (en) * 1985-12-13 1988-11-29 Hitachi, Limited Data transfer apparatus between input/output devices and main storage with channel devices being of a concentrated type and stand-alone type
US4852083A (en) * 1987-06-22 1989-07-25 Texas Instruments Incorporated Digital crossbar switch
US4885799A (en) * 1987-07-01 1989-12-05 Motorola, Inc. Load pull isolation switch for a fast locking synthesizer
US4903259A (en) * 1987-07-24 1990-02-20 Nec Corporation Time-division multiplex switching network
US5046041A (en) * 1987-12-17 1991-09-03 Automobiles Peugeot Device for transmitting information between a plurality of elements of an automobile vehicle, and a central information processing unit
US5109333A (en) * 1988-04-15 1992-04-28 Hitachi, Ltd. Data transfer control method and apparatus for co-processor system
US5058072A (en) * 1988-06-01 1991-10-15 Nec Corporation Semiconductor memory device with high speed sensing facility
US4987319A (en) * 1988-09-08 1991-01-22 Kawasaki Steel Corporation Programmable input/output circuit and programmable logic device
US5079693A (en) * 1989-02-28 1992-01-07 Integrated Device Technology, Inc. Bidirectional FIFO buffer having reread and rewrite means
US5087900A (en) * 1990-11-19 1992-02-11 Reliability Incorporated Transmission line network for multiple capacitive loads
US5191656A (en) * 1991-08-29 1993-03-02 Digital Equipment Corporation Method and apparatus for shared use of a multiplexed address/data signal bus by multiple bus masters

Cited By (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5638521A (en) * 1992-10-12 1997-06-10 Leunig Gmbh Apparatus using a parallel interface for data transfer between a plurality of computers, as well as for transfer of data from computers to shared peripheral devices
US5611053A (en) * 1994-01-21 1997-03-11 Advanced Micro Devices, Inc. Apparatus and method for integrating bus master ownership of local bus load by plural data transceivers
US5572685A (en) * 1994-03-23 1996-11-05 International Computers Limited Computer system
US5661413A (en) * 1994-06-06 1997-08-26 Matsushita Electric Industrial Co., Ltd. Processor utilizing a low voltage data circuit and a high voltage controller
US5793656A (en) * 1994-06-30 1998-08-11 Hughes Electronics Corporation Application-specific integrated circuits having programming functions
US5664123A (en) * 1994-09-06 1997-09-02 Pitney Bowes Inc. Digital communication I/O port
US6029242A (en) * 1995-08-16 2000-02-22 Sharp Electronics Corporation Data processing system using a shared register bank and a plurality of processors
US5783963A (en) * 1996-02-29 1998-07-21 Lexmark International, Inc. ASIC with selectable output drivers
US5949982A (en) * 1997-06-09 1999-09-07 International Business Machines Corporation Data processing system and method for implementing a switch protocol in a communication system
US6101561A (en) * 1998-02-06 2000-08-08 International Business Machines Corporation System for providing an increase in digital data transmission rate over a parallel bus by converting binary format voltages to encoded analog format currents
US6530033B1 (en) * 1999-10-28 2003-03-04 Hewlett-Packard Company Radial arm memory bus for a high availability computer system
US8769231B1 (en) * 2008-07-30 2014-07-01 Xilinx, Inc. Crossbar switch device for a processor block core
US20150205740A1 (en) * 2012-01-31 2015-07-23 Hewlett-Packard Development Company, L.P. Flexible port configuration based on interface coupling
US10140231B2 (en) * 2012-01-31 2018-11-27 Hewlett-Packard Development Company, L.P. Flexible port configuration based on interface coupling

Also Published As

Publication number Publication date
US5526497A (en) 1996-06-11

Similar Documents

Publication Publication Date Title
US5418911A (en) Data path switch method and apparatus that provides capacitive load isolation
US5625780A (en) Programmable backplane for buffering and routing bi-directional signals between terminals of printed circuit boards
US6182178B1 (en) Method and system for supporting peripheral component interconnect (PCI) peer-to-peer access across a PCI host bridge supporting multiple PCI buses
US7424552B2 (en) Switch/network adapter port incorporating shared memory resources selectively accessible by a direct execution logic element and one or more dense logic devices
US6081863A (en) Method and system for supporting multiple peripheral component interconnect PCI buses by a single PCI host bridge within a computer system
KR100288038B1 (en) Pipeline semiconductor device suitable for ultra-large scale integration
EP0164495A2 (en) Duplex cross-point switch
US6339806B1 (en) Primary bus to secondary bus multiplexing for I2C and other serial buses
US9363203B2 (en) Modular interconnect structure
US5740385A (en) Low load host/PCI bus bridge
CA2483541A1 (en) Adaptive processor architecture incorporating a field programmable gate array control element having at least one embedded microprocessor core
EP0448624B1 (en) Bus interface controller for computer graphics
US6580288B1 (en) Multi-property microprocessor with no additional logic overhead to shared pins
JP3574061B2 (en) Processor bus structure
EP0344677B1 (en) Microprocessor system
US5371863A (en) High speed processor bus extension
US6311247B1 (en) System for bridging a system bus with multiple PCI buses
US5222227A (en) Direct memory access controller for a multi-microcomputer system
JPS62212860A (en) Data transfer circuit
EP0929042B1 (en) Bus controller in a data processor
EP0976055B1 (en) Data-path architecture for speed
US20050216640A1 (en) Processor bus arrangement
JP2000047766A (en) Method and device for parallel data transmission, and method and device for collision prevention in parallel bus system
KR100238179B1 (en) General purpose data path control apparatus
JPH0561812A (en) Information processing system

Legal Events

Date Code Title Description
AS Assignment

Owner name: INTEL CORPORATION, CALIFORNIA

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST.;ASSIGNORS:ZILKA, ANTHONY M.;TARAGHI, MASSOUD;PRINCE, PAUL E.;REEL/FRAME:006156/0751

Effective date: 19920608

STCF Information on status: patent grant

Free format text: PATENTED CASE

CC Certificate of correction
FEPP Fee payment procedure

Free format text: PAYOR NUMBER ASSIGNED (ORIGINAL EVENT CODE: ASPN); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY

FPAY Fee payment

Year of fee payment: 4

FPAY Fee payment

Year of fee payment: 8

FEPP Fee payment procedure

Free format text: PAYER NUMBER DE-ASSIGNED (ORIGINAL EVENT CODE: RMPN); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY

Free format text: PAYOR NUMBER ASSIGNED (ORIGINAL EVENT CODE: ASPN); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY

FPAY Fee payment

Year of fee payment: 12